A novel generative adversarial net for calligraphic tablet images denoising

Chinese calligraphic images have important historical and artistic value, but natural weathering and man-made decay severely damage these works, thus image denoising is an important topic to be addressed. Traditional denoising methods still leave room for improvement. In this paper, image denoising...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Multimedia tools and applications Jg. 79; H. 1-2; S. 119 - 140
Hauptverfasser: Zhang, Jiulong, Guo, Mingtao, Fan, Jianping
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.01.2020
Springer Nature B.V
Schlagworte:
Architecture
Calligraphy
Computer Communication Networks
Computer Science
Computer simulation
Computer vision
Cultural heritage
Data processing
Data Structures and Information Theory
Embedded systems
Image reconstruction
Multimedia
Multimedia Information Systems
Noise
Noise reduction
Pattern recognition
Special Purpose and Application-Based Systems
Training
Calligraphic images
GAN
Residual dense blocks
Image denoising
ISSN:1380-7501, 1573-7721
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Chinese calligraphic images have important historical and artistic value, but natural weathering and man-made decay severely damage these works, thus image denoising is an important topic to be addressed. Traditional denoising methods still leave room for improvement. In this paper, image denoising is modeled as generation of clean image by using GAN (Goodfellow I et al. Advances in Neural Information Processing Systems 2672–2680, 2014 ) with an embedment of residual dense blocks (Zhang Y et al. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 ) that was formerly used for super resolution reconstruction. Meanwhile, a new type of noise is defined to simulate the real noise, and is used for compensation of unpaired data in the training set for GAN. The new structure, used with some preprocessing and training methods, yield satisfactory results compared to known denoising methods.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-019-08052-8